Analysts developing data models face a number of key data challenges, including biases – such as confirmation and availability biases – bad data, and model inaccuracies. One key type of data model, known as machine learning, allows the user to query the model for answers to simple questions. This eCourse provides an overview of major pitfalls in developing data models and discusses the importance of ML in detail.

On completion of this course, you will be able to:
- Recognise the importance of alternative data, including big data and expert data
- Recall how biases, bad data, and model inaccuracies can all affect the handling of data
- Identify the key features of both supervised and unsupervised machine learning (ML)
- Recognise how dimension reduction reduces the dimension of a data set and how data clustering groups large amounts of multi-dimensional data

Quantitative Trading – Data & Machine Learning
Topic 1: Overview
Topic 2: Alternative Data
Topic 3: Big Data & Expert Data
Topic 4: Biases
Topic 5: Machine Learning (ML)
Topic 6: Supervised & Unsupervised ML
Topic 7: Dimension Reduction
Topic 8: Data Clustering